skills/garethmanning/claude-education-skills/formative-assessment-technique-selector/Gen Agent Trust Hub
formative-assessment-technique-selector
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: Comprehensive analysis of the skill content reveals no malicious logic, obfuscation, or unauthorized data access patterns. The skill adheres to its stated educational purpose.
- [NO_CODE]: The skill consists entirely of YAML metadata and markdown instructions; it does not contain any scripts, binaries, or executable logic.
- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it ingests untrusted data through variables such as
{{student_profiles}}and{{learning_moment}}. - Ingestion points: Template variables in the
Promptsection ofSKILL.md. - Boundary markers: No specific delimiters or instructions to ignore embedded commands are present.
- Capability inventory: The skill has no tool-calling or shell execution capabilities and is restricted via the
disable-model-invocation: trueconfiguration. - Sanitization: No input validation or filtering is performed on the provided variables. Given the lack of actionable capabilities, this surface poses no significant security risk.
Audit Metadata